Papers › DirectPose: Direct End-to-End Multi-Person Pose Estimation

DirectPose: Direct End-to-End Multi-Person Pose Estimation

18 Nov 2019arXiv:1911.07451archive 2025-07-28

Zhi Tian, Hao Chen, Chunhua Shen

We propose the first direct end-to-end multi-person pose estimation framework, termed DirectPose. Inspired by recent anchor-free object detectors, which directly regress the two corners of target bounding-boxes, the proposed framework directly predicts instance-aware keypoints for all the instances from a raw input image, eliminating the need for heuristic grouping in bottom-up methods or bounding-box detection and RoI operations in top-down ones. We also propose a novel Keypoint Alignment (KPAlign) mechanism, which overcomes the main difficulty: lack of the alignment between the convolutional features and predictions in this end-to-end framework. KPAlign improves the framework's performance by a large margin while still keeping the framework end-to-end trainable. With the only postprocessing non-maximum suppression (NMS), our proposed framework can detect multi-person keypoints with or without bounding-boxes in a single shot. Experiments demonstrate that the end-to-end paradigm can achieve competitive or better performance than previous strong baselines, in both bottom-up and top-down methods. We hope that our end-to-end approach can provide a new perspective for the human pose estimation task.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

IDEA-Research/UniPose mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to X-Pose: Detecting Any Keypoints (arXiv:2310.08530; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
Pxtri2156/AdelaiDet_v2 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Conditional Convolutions for Instance Segmentation (arXiv:2003.05664; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
aim-uofa/AdelaiDet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
aim-uofa/adet mentioned on GitHubpytorchSyntology: not harvested report
blueardour/AdelaiDet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
idea-research/x-pose mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to X-Pose: Detecting Any Keypoints (arXiv:2310.08530; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
quangvy2703/ABCNet-ESRGAN-SRTEXT mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
zhubinQAQ/Ins mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keypoint Detection COCO test-dev DirectPose (ResNet-101) AP 64.8 #13 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev DirectPose (ResNet-101) AP50 87.8 #13 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev DirectPose (ResNet-101) AP75 71.1 #13 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev DirectPose (ResNet-101) APL 71.5 #13 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev DirectPose (ResNet-101) APM 60.4 #13 of 16 Archive leaderboard report
Pose Estimation COCO test-dev DirectPose (ResNet-101) AP 63.3 #42 of 47 Archive leaderboard report
Pose Estimation COCO test-dev DirectPose (ResNet-101) AP50 86.7 #42 of 47 Archive leaderboard report
Pose Estimation COCO test-dev DirectPose (ResNet-101) AP75 69.4 #42 of 47 Archive leaderboard report
Pose Estimation COCO test-dev DirectPose (ResNet-101) APL 71.2 #42 of 47 Archive leaderboard report
Pose Estimation COCO test-dev DirectPose (ResNet-101) APM 57.8 #42 of 47 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections